INDEX

Explanations

programming-related expressions and assertions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 العنوان

-0.50

ftagPool

-0.48

 всеми

-0.48

Personendaten

-0.48

MigrationBuilder

-0.47

 informatique

-0.45

съ

-0.44

scalatest

-0.44

###

-0.44

fo

-0.43

POSITIVE LOGITS

expandindo

0.78

 AssemblyCulture

0.73

ContentAlignment

0.70

 null

0.69

TypedDataSet

0.68

titleMargin

0.65

 empty

0.64

numerusform

0.63

giveness

0.63

Хьажоргаш

0.62

Activations Density 0.906%

programming-related expressions and assertions

No Comments

No Known Activations